{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UDZ6WVSFISXGWI5MXPSB4N3734","short_pith_number":"pith:UDZ6WVSF","schema_version":"1.0","canonical_sha256":"a0f3eb564544ae6b23acbbe41e377fdf2554a69763656487141b22b7bf2c2882","source":{"kind":"arxiv","id":"2608.03487","version":1},"attestation_state":"computed","paper":{"title":"RAG-Stack: Co-Optimizing RAG Serving Performance and Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Haiqiang Zhang, Tao Zhang, Wanting Li, Wenqi Jiang, Yuanqing Lei","submitted_at":"2026-08-04T11:23:19Z","abstract_excerpt":"Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledge-intensive applications. Modern RAG systems, however, expose many configuration choices, such as retrieval indexes, model selections, and how models invoke retrieval. Each configuration yields a different trade-off between answer quality and serving performance, making it challenging to choose the optimal setting for a specific application deployment. We present RAG-Stack, a framework for efficiently discovering qua"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-04T11:23:19Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f9f970a25df19b8a9c448c728324f0354cc1436af14c902e38b62287e448446a","abstract_canon_sha256":"c1becee0a79625dbfe3079376cb159d2398df87950dc3b47972dad1275fac342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:57.209781Z","signature_b64":"gwRSv0O2irOHQ1+qyi+85WQouOntoKuxD5+xbOH4AOV+wE/C3aPbJ/bsS/EEclrrD+0Cqd5n1myHwoMd2uZRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f3eb564544ae6b23acbbe41e377fdf2554a69763656487141b22b7bf2c2882","last_reissued_at":"2026-08-05T01:35:57.208042Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:57.208042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG-Stack: Co-Optimizing RAG Serving Performance and Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Haiqiang Zhang, Tao Zhang, Wanting Li, Wenqi Jiang, Yuanqing Lei","submitted_at":"2026-08-04T11:23:19Z","abstract_excerpt":"Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledge-intensive applications. Modern RAG systems, however, expose many configuration choices, such as retrieval indexes, model selections, and how models invoke retrieval. Each configuration yields a different trade-off between answer quality and serving performance, making it challenging to choose the optimal setting for a specific application deployment. We present RAG-Stack, a framework for efficiently discovering qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03487","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.03487/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03487","created_at":"2026-08-05T01:35:57.208782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03487v1","created_at":"2026-08-05T01:35:57.208782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03487","created_at":"2026-08-05T01:35:57.208782+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDZ6WVSFISXG","created_at":"2026-08-05T01:35:57.208782+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDZ6WVSFISXGWI5M","created_at":"2026-08-05T01:35:57.208782+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDZ6WVSF","created_at":"2026-08-05T01:35:57.208782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734","json":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734.json","graph_json":"https://pith.science/api/pith-number/UDZ6WVSFISXGWI5MXPSB4N3734/graph.json","events_json":"https://pith.science/api/pith-number/UDZ6WVSFISXGWI5MXPSB4N3734/events.json","paper":"https://pith.science/paper/UDZ6WVSF"},"agent_actions":{"view_html":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734","download_json":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734.json","view_paper":"https://pith.science/paper/UDZ6WVSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03487&json=true","fetch_graph":"https://pith.science/api/pith-number/UDZ6WVSFISXGWI5MXPSB4N3734/graph.json","fetch_events":"https://pith.science/api/pith-number/UDZ6WVSFISXGWI5MXPSB4N3734/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734/action/storage_attestation","attest_author":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734/action/author_attestation","sign_citation":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734/action/citation_signature","submit_replication":"https://pith.science/pith/UDZ6WVSFISXGWI5MXPSB4N3734/action/replication_record"}},"created_at":"2026-08-05T01:35:57.208782+00:00","updated_at":"2026-08-05T01:35:57.208782+00:00"}